metadata
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: t5-big-finetuned-iwslt2017
results: []
language:
- en
- de
t5-big-finetuned-iwslt2017
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.1846
- Bleu: 0.186
- Gen Len: 25.4842
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
- IWSLT-2017-01: https://wit3.fbk.eu/2017-01
- IWSLT-2017-01-B: https://wit3.fbk.eu/2017-01-b
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
Training results
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.1.2
- Datasets 2.19.0
- Tokenizers 0.19.1